KR20230174610A - Method and apparatus for positioning - Google Patents

Abstract

A location determination method and device are disclosed. A location determination method according to an embodiment of the present disclosure includes the steps of receiving a signal from a tag in a movable anchor set capable of moving within a set range in three-dimensional space, and based on a homography algorithm, It may include converting the tag signal information into a three-dimensional space based on the mobile anchor set and deriving the coordinates of the tag in the three-dimensional space based on the mobile anchor set.

Description

Location determination method and device {METHOD AND APPARATUS FOR POSITIONING}

The present disclosure relates to a positioning method and device that performs positioning in an arbitrary space through a portable UWB anchor set based on ultra-wide band (UWB) wireless technology. .

In general, Ultra-Wide Band (UWB) is a system that occupies an occupied bandwidth of more than 20% of the center frequency or a wireless system that occupies an occupied bandwidth of 500 MHz or more to distinguish it from narrow-band systems and broadband systems described as 3G cellular technology. It refers to transmission technology.

While existing wireless technologies such as Bluetooth use a specific frequency band of 2.4GHz and wireless LAN use a specific frequency band of 5GHz, UWB can use a wide frequency band ranging from 3.1GHz to 10.6GHz, which can dramatically solve the problem of frequency shortage.

The maximum transmission distance is 1km, which is 10 times longer than wireless LAN, and the service coverage is wide, making it possible to implement two-way services such as communication for automobiles and communication for disaster relief. In addition, other representative advantages of UWB are that the power consumption is 1/100th of that of mobile phones or wireless LANs, and the cost of commercializing the technology is low.

General positioning technology based on UWB configures space by installing UWB Anchors at fixed locations and specifying coordinates based on distance. The distance is predicted based on the signal emitted by the UWB Tag located inside the configured space or outside the adjacent space, and the location is measured using algorithms such as triangulation/trilateration/intersection of straight lines along with the fixed location information of the UWB anchor. I do it.

In other words, most UWB anchors are installed at the edge or corner of the space where the UWB tag is to be located to define the space to be measured. However, measurement of UWB tags will be possible if there are no special obstacles outside the space where the signal reaches.

The above-mentioned background technology is technical information that the inventor possessed for deriving the present invention or acquired in the process of deriving the present invention, and cannot necessarily be said to be known art disclosed to the general public before filing the application for the present invention.

Prior Art 1: Korean Patent Publication No. 10-2009791 (2019.08.06) Prior Art 2: Korean Patent Publication No. 10-0954169 (2010.04.14)

One task of the embodiment of the present disclosure is to install a UWB anchor at a fixed location in a specific space to measure the distance and status of signals received/collected (or transmitted/received) from a tag in a certain space to determine the location of the tag. To solve the inconveniences and limitations, positioning can be performed in any space through a portable UWB anchor set.

One task of the embodiment of the present disclosure is to determine the location of a UWB tag that exists in a place where a UWB anchor cannot be installed in advance (eg, a building, a mountain, the sea, a cave, etc.).

One task of the embodiment of the present disclosure is to identify signal states for reflection/transmission/refraction and perform location determination using an artificial neural network to respond to various environments.

The purpose of the embodiments of the present disclosure is not limited to the problems mentioned above, and other objects and advantages of the present invention that are not mentioned can be understood through the following description and can be understood more clearly by the embodiments of the present invention. will be. Additionally, it will be appreciated that the objects and advantages of the present invention can be realized by means and combinations thereof as indicated in the patent claims.

A location determination method according to an embodiment of the present disclosure includes the steps of receiving a signal from a tag in a movable anchor set capable of moving within a set range in three-dimensional space, and based on a homography algorithm, It may include converting the tag signal information into a three-dimensional space based on the mobile anchor set and deriving the coordinates of the tag in the three-dimensional space based on the mobile anchor set.

In addition, another method for implementing the present invention, another system, and a computer-readable recording medium storing a computer program for executing the method may be further provided.

Other aspects, features and advantages in addition to those described above will become apparent from the following drawings, claims and detailed description of the invention.

According to an embodiment of the present disclosure, for indoor/outdoor location positioning, WiFi/BLE Scanners or UWB Anchors are not installed and configured in a certain location, but rather an array sensor integrating several Lidars and Likewise, by configuring a set of mobile anchors like a three-dimensional sensor for positioning and applying it to immediate positioning, UWB anchors can be installed at a fixed location in a specific space to monitor signals received/collected (or transmitted/received) from tags in a certain space. It can solve the inconvenience and limitations of having to determine the location of the tag by measuring the distance and status, and can be used for UWB tags in places where UWB anchors cannot be installed in advance (e.g., buildings, mountains, the sea, caves, etc.). Make it possible to determine the location.

In addition, according to an embodiment of the present disclosure, by using an artificial neural network to identify signal states for reflection/transmission/refraction and perform positioning, it is possible to respond to various environments and improve positioning accuracy.

The effects of the present disclosure are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram schematically showing a location determination system according to an embodiment.
Figure 2 is an example diagram for explaining positioning in a three-dimensional space according to an embodiment.
Figure 3 is a schematic diagram illustrating positioning based on a mobile anchor set according to an embodiment.
Figure 4 is a block diagram schematically showing a location determination device according to an embodiment.
Figure 5 is an exemplary diagram schematically showing a movable anchor set according to an embodiment.
Figure 6 is an example diagram illustrating positioning based on a movable anchor set that can be separated into two sets according to an embodiment.
Figure 7 is a flowchart for explaining a location determination method according to an embodiment.

The advantages and features of the present disclosure and methods for achieving them will become clear by referring to the embodiments described in detail together with the accompanying drawings.

However, the present disclosure is not limited to the embodiments presented below, but may be implemented in various different forms, and should be understood to include all conversions, equivalents, and substitutes included in the spirit and technical scope of the present disclosure. . The embodiments presented below are provided to ensure that the present disclosure is complete and to fully inform those skilled in the art of the disclosure of the scope of the disclosure. In describing the present disclosure, if it is determined that a detailed description of related known technologies may obscure the gist of the present disclosure, the detailed description will be omitted.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the present disclosure. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof. Terms such as first, second, etc. may be used to describe various components, but the components should not be limited by these terms. The above terms are used only for the purpose of distinguishing one component from another.

Hereinafter, embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. In the description with reference to the accompanying drawings, identical or corresponding components are assigned the same drawing numbers and duplicate descriptions thereof are omitted. I decided to do it.

FIG. 1 is a diagram schematically showing a positioning system according to an embodiment, FIG. 2 is an example diagram for explaining positioning in a three-dimensional space according to an embodiment, and FIG. 3 is a mobile positioning system according to an embodiment. This is a schematic example diagram to explain anchor set-based location determination.

Referring to FIG. 1, the location determination system 1 may include a location determination device 100, a user terminal 200, a server 300, and a network 400.

The positioning system 1 of one embodiment is a system that performs positioning of a UWB tag (hereinafter referred to as tag) in an arbitrary space based on a movable UWB anchor set (hereinafter referred to as anchor set). UWB is a technology that enables precise location determination. However, in order to determine the location in a certain space, anchors that receive/collect signals must be installed in fixed locations, and the installed location is recorded to avoid the inconvenience and limitations of measuring the distance and status of the signal received from the tag. Have.

Most anchors are installed at the edge or corner of the space where the tag's location is to be measured, defining the space to be measured. However, tag measurement may be possible outside the space where the signal reaches if there is no special shielding (obstacle).

Accordingly, in one embodiment, an anchor set is configured as shown in FIG. 2 to determine the position of the tag, but it is reduced to a small movable space as shown in FIG. 3 and projected into the space to be actually measured ( Projection) can be used to determine the location of the tag.

In other words, the location determination system 1 performs location determination based on UWB, and unlike the general method of installing anchors in a specific location and configuring the space to predict the location of the tag in the space, a set of anchors can be carried. It is possible to construct a space based on projection and homography algorithms outside the space where you want to measure tags.

In addition, the positioning system 1 determines the characteristics of signals according to materials based on deep neural networks for materials (e.g., cement, glass, wood, etc.) that interfere with positioning and signal progression. By classifying, the location of the UWB tag in the target space can be determined. At this time, a linear regression neural network may be applied to the deep neural network, but is not limited to this.

Meanwhile, in one embodiment, a TDoA (Time Difference of Arrival) method predicts the distance through the time difference received by anchors based on the moving speed of radio waves in the air, and a TDoA (Time Difference of Arrival) method that predicts the distance based on the transmission and reception time between anchors and tags. Positioning can be performed based on the TWR (Two Way Ranging) method. When the TDoA method is applied, signals are received (or collected) from the anchor, and when the TWR method is applied, signals can be transmitted and received from the anchor. .

However, in one embodiment, it is not limited to the TDoA method or the TWR method, but as an example in which the TDoA method is applied, it is described as receiving a signal from the anchor. Additionally, in addition to TDoA and TWR, methods such as Angle of Arrival (AoA) and Angle of Departure (AoD) may be applied.

In other words, the location determination system 1 of one embodiment is a system for determining the location of a tag that exists in a place where anchors cannot be installed in advance, such as a building, mountain, sea, cave, etc.

In other words, the positioning system (1) provides immediate positioning in places where anchor installation is difficult or the position must be changed frequently, such as confirming the position of workers at a construction site, confirming the position of firefighters at a fire site, or searching for survivors in the natural environment. It can be used for any purpose.

Therefore, in the positioning system 1, there is no need to install anchors in advance, and the anchors can be easily reused because their positions can be moved.

In addition, the positioning system 1 of one embodiment determines the signal status of reflection, transmission, and refraction, which must be solved in order to implement a technology for positioning the tag by moving and positioning anchors outside the space where the tag to be measured is located. It is possible to respond to various environments by using artificial neural networks such as deep neural networks to perform location determination.

Meanwhile, as described above, in UWB, the distance is measured by the TDoA method and the TWR method, which predict the distance through the time difference received by anchors based on the moving speed of radio waves in the air. In this case, in one embodiment, the anchors Since the embodiment is located outside the space for positioning, the status of the received signal for obstacles must be determined.

Accordingly, in one embodiment, anchors use RSSI (Received Signal Strength Indicator) and RSSI for LOS/NLOS (Line of Sight/Non Line of Sight), which predicts the state of the received signal Positioning accuracy can be improved by referring to the signal status between anchors.

Below, the temporary line/invisible line will be briefly explained.

Non-line-of-sight radio propagation can occur outside the normal line of sight between a transmitter and receiver, such as ground-reflection. Near-line-of-sight (NLOS) conditions may refer to partial obstruction by physical objects present in the innermost Fresnel zone. Here, radio waves mean when radio waves move or propagate from one point to another in a vacuum or to various parts of the atmosphere. It is a type of electromagnetic wave and, like light waves, has the phenomena of reflection, refraction, diffraction, absorption, polarization, and scattering. can be influenced by

Obstacles that typically cause non-line-of-sight transmission may include buildings, trees, hills, mountains, and, in some cases, high-voltage power lines. Some of these obstacles reflect certain radio frequencies, while others simply absorb or distort the signals. However, both cases can limit the use of many types of wireless transmission, especially when power budgets are low.

Low power levels at the receiver can reduce the likelihood of successfully receiving a transmission. Low power levels can be caused by three reasons: low transmission levels, distant transmitters, and obstacles between the transmitter and receiver that prevent a clear path.

Non-line-of-sight lines lower the effective received power. Near-line-of-sight can usually be handled using better antennas, but non-line-of-sight usually requires alternate or multipath propagation methods.

How to achieve effective non-line-of-sight networking has become one of the key questions in modern computer networking. Currently, the most common way to handle non-line-of-sight conditions in wireless computer networks is to bypass the non-line-of-sight conditions and place relays in additional locations to direct wireless transmissions around obstacles. Some more advanced non-line-of-sight transmission methods use multipath signal propagation, allowing radio signals to bounce off other nearby objects to reach the receiver.

Non-line-of-sight is a term often used in wireless communications to describe a wireless channel or link in which there is no visual line of sight between the transmitting and receiving antennas. In this context, line-of-sight is a straight line that is clear of any form of visual obstruction, even if it is too far away to be seen by the human eye, or a virtual line-of-sight (e.g., a straight line that passes through a visual obstruction) that leaves enough transmission for the radio waves to be detected. You can. The electrical properties of the transmission medium that affect radio propagation vary greatly and can therefore affect the quality of operation of the radio channel over non-line-of-sight paths.

Meanwhile, in one embodiment, users can access an application or website implemented on the user terminal 200, request a location determination service, and receive location determination results.

This user terminal 200 can receive location determination services through an authentication process after accessing the location determination service application or location determination service site. The authentication process may include, but is not limited to, authentication of inputting user information such as membership registration, authentication of a user terminal, etc., and is not limited to this, but may include accessing a link transmitted from the location determination device 100 and/or the server 300. The authentication process may be performed simply by doing so.

Meanwhile, in one embodiment, the user terminal 200 may be implemented with a tag to determine its location.

These user terminals 200 include desktop computers, smartphones, laptops, tablet PCs, smart TVs, mobile phones, personal digital assistants (PDAs), laptops, media players, micro servers, and global positioning system (GPS) devices operated by the user. , e-book terminals, digital broadcasting terminals, navigation devices, kiosks, MP3 players, digital cameras, home appliances, and other mobile or non-mobile computing devices, but are not limited thereto.

Additionally, the user terminal 200 may be a wearable terminal such as a watch, glasses, hair band, or ring equipped with a communication function and data processing function. The user terminal 200 is not limited to the above-described content, and any terminal capable of web browsing may be used without limitation.

Meanwhile, in one embodiment, the location determination system 1 may be implemented by the location determination device 100 and/or the server 300. In other words, the location determination device 100 may be partially or entirely implemented as the server 300.

That is, the location determination device 100 may be implemented in the server 300, where the server 300 is a server for operating the location determination system 1 including the location determination device 100 or the location determination device 100. ) may be a server that implements part or all of it.

In one embodiment, the server 300 receives a location determination service request, performs UWB-based location determination based on a preset algorithm, and provides location determination results to the location determination device 100. It may be a server that controls the operation of .

In addition, the server 300 manages, for example, not only the configuration of the location determination device 100, but also new registration of related devices, network environment, etc., to facilitate service provision and management in the location location service platform. It may be a server in charge of operating various devices so that they can be performed.

Additionally, the server 300 may be a database server that provides data for operating the location determination device 100. Additionally, the server 300 may include a web server, an application server, or a deep learning network provision server.

Additionally, the server 300 may include a big data server and an AI server required to apply various artificial intelligence algorithms, and a calculation server that performs calculations of various algorithms.

Additionally, in this embodiment, the server 300 may include the servers described above or may be networked with these servers. That is, in this embodiment, the server 300 may include the above-mentioned web server and AI server or may be networked with these servers.

In the location determination system 1, the location determination device 100 and the server 300 may be connected by a network 400. These networks 400 include, for example, wired networks such as local area networks (LANs), wide area networks (WANs), metropolitan area networks (MANs), and integrated service digital networks (ISDNs), or wireless LANs, CDMA, Bluetooth, and satellite communications. It may encompass wireless networks such as, but the scope of the present disclosure is not limited thereto. Additionally, the network 400 may transmit and receive information using short-range communication and/or long-distance communication.

Additionally, the network 400 may include connections of network elements such as hubs, bridges, routers, switches, and gateways. Network 400 may include one or more connected networks, including public networks such as the Internet and private networks such as secure enterprise private networks, such as a multi-network environment. Access to network 400 may be provided through one or more wired or wireless access networks. Furthermore, the network 400 may support an IoT (Internet of Things) network and/or 5G communication that exchanges and processes information between distributed components such as objects.

However, in one embodiment, the network 400 may be implemented with ultra-wide band (UWB) wireless technology.

Figure 4 is a block diagram schematically showing a location determination device according to an embodiment.

Referring to FIG. 4 , the location determination device 100 may include a communication interface 110, a user interface 120, a memory 130, and a processor 140.

The communication unit 110 may work with the network 400 to provide a communication interface necessary to provide transmission and reception signals between external devices in the form of packet data. Additionally, the communication unit 110 may be a device that includes hardware and software necessary to transmit and receive signals such as control signals or data signals through wired or wireless connections with other network devices.

This communication interface 110 can support various object intelligence communications (IoT (internet of things), IoE (internet of everything), IoST (internet of small things), etc.), M2M (machine to machine) communication, V2X ( It can support vehicle to everything communication (D2D) communication and D2D (device to device) communication.

That is, the processor 140 can receive various data or information from an external device connected through the communication unit 110, and can also transmit various data or information to the external device. And, the communication interface 110 may include at least one of a UWB module, a WiFi module, a Bluetooth module, a wireless communication module, and an NFC module.

The user interface 120 may include an input interface through which user requests and commands for the location determination service platform provided by the location determination device 100 are input.

In addition, the user interface 120 provides user requests and commands for controlling the operation of the positioning device 100 (e.g., changing the learning parameters of the algorithm, entering the position of the mobile anchor set, changing various settings and conditions for positioning, etc.) It may include an input interface through which input is input.

Additionally, the user interface 120 may include an output interface through which location determination results, etc. are output. That is, the user interface 120 can output results according to user requests and commands. The input interface and output interface of this user interface 120 may be implemented in the same interface.

The memory 130 stores various information necessary for controlling (computing) the operation of the location determination device 100 and/or the server 300, and can store control software, and may include a volatile or non-volatile recording medium. You can.

The memory 130 is connected to one or more processors 140 through an electrical or internal communication interface and, when executed by the processor 140, causes the processor 140 to control the location determination device 100. Codes can be saved.

Here, the memory 130 may include a non-transitory storage medium such as magnetic storage media or flash storage media, or a temporary storage medium such as RAM, but is within the scope of the present invention. is not limited to this. This memory 130 may include internal memory and/or external memory, volatile memory such as DRAM, SRAM, or SDRAM, one time programmable ROM (OTPROM), PROM, EPROM, EEPROM, mask ROM, flash ROM, Non-volatile memory, such as NAND flash memory, or NOR flash memory, SSD. It may include a flash drive such as a compact flash (CF) card, SD card, Micro-SD card, Mini-SD card, Xd card, or memory stick, or a storage device such as an HDD.

Additionally, information related to an algorithm for performing learning according to the present disclosure may be stored in the memory 130. In addition, various information necessary within the scope of achieving the purpose of the present disclosure may be stored in the memory 130, and the information stored in the memory 130 may be updated as it is received from a server or external device or input by the user. It may be possible.

The processor 140 may control the overall operation of the location determination device 100. Specifically, the processor 140 is connected to the configuration of the location determination device 100 including the memory 130, and executes at least one command stored in the memory 130 to control the overall operation of the location determination device 100. It can be controlled with .

The processor 140 may be implemented in various ways. For example, the processor 140 may include an application specific integrated circuit (ASIC), an embedded processor, a microprocessor, hardware control logic, a hardware finite state machine (FSM), and a digital signal processor. Processor, DSP).

The processor 140 is a type of central processing unit and can control the operation of the positioning device 100 by driving control software mounted on the memory 130. Processor 140 may include all types of devices capable of processing data. Here, 'processor' may mean, for example, a data processing device built into hardware that has a physically structured circuit to perform a function expressed by code or instructions included in a program.

FIG. 5 is an exemplary diagram schematically showing a mobile anchor set according to an embodiment, and FIG. 6 is an exemplary diagram for explaining positioning based on a mobile anchor set that can be separated into two sets according to an exemplary embodiment.

The processor 140 can project the 3D space to be measured onto the flat space of the sensor (i.e. anchor) in order to measure or predict the 3D position or the distance to the corresponding object for the data acquired in the measurement space. This is also called projection technology. For example, projection technology is being implemented in products such as digital cameras and Microsoft's Kinect.

This projection technology records location and distance information by projecting information about the three-dimensional space to be acquired onto the plane of the sensor (i.e., anchor). However, in the case of a relatively flat space like a camera, the depth (or distance) value cannot be recorded, so multiple images can be used or the distance can be predicted by specifying the size of the object.

Based on this technology, in one embodiment, a three-dimensional space can be constructed using several anchors, and the position can be measured based on signal information of the tag acquired from the three-dimensional space to be measured.

That is, the processor 140 uses a set of three-dimensional anchors configured to be movable, acquires the three-dimensional space to be measured using projection technology (i.e., projection matrix-based technology), and uses a homography algorithm (homography matrix-based). The three-dimensional space can be reconstructed based on the plane where the anchor set is located.

Therefore, in one embodiment, the anchor that receives the signal emitted by the tag can be configured to be projectable. This method is similar to AOA, which uses the difference in speed of radio waves moving through the air, but since AOA-based anchors are complicated to implement, in one embodiment, a TDoA anchor may be used.

Meanwhile, in one embodiment, as shown in FIG. 5, two sets of anchors can be used to measure the distance like a camera for the space to be measured (for example, 'A and B'). and two sets of 'C and D').

At this time, the first anchor set may be responsible for positioning on the plane, and the second anchor set may be responsible for correction for reflection, transmission, and refraction in reception from the first anchor set, and at the same time, the space on the measured plane ( height) can be configured.

That is, in one embodiment, in order to receive a signal from a tag and construct a projected space, a movable anchor set including two anchor sets for plane positioning and two anchor sets for plane correction and space construction can be used. there is.

However, the present invention is not limited to this, and each anchor set may include three or more anchors, and at least one anchor may be implemented as the same anchor.

Meanwhile, the problem with the existing AOA anchor is that due to the measurement method, short-distance measurement is generally performed, and long-distance measurement is difficult to measure time difference due to obstacles or acute angles, which can lead to severe errors. This technology, like the UWB Anchor for AOA, solves the problems of long-distance positioning due to high production costs and measurement errors.

As shown in FIG. 6, the processor 140 may measure a first distance value, which is the planar distance (D) with respect to the horizontal, between the A and B anchors (first anchor set) for the tag P. In addition, the processor 140 can measure a second distance value, which is the planar distance (D') with respect to the vertical, of the C and D anchors (second anchor set) located behind the A and B anchors. Here, rear means that it is located behind the tag P in the direction facing it.

At this time, the depth difference between the first anchor set and the second anchor set may occur as a signal difference in LOS/NLOS due to obstacles in the space to be measured. Accordingly, the processor 140 can adjust the depth based on the RSSI value received together. The depth value can be defined as a specified projection layer between the actual tag's location and the anchor set.

In one embodiment, processor 140 derives x coordinates in the plane projected by the received signals of the first anchor set (between A and B) and the received signals of the second anchor set (between C and D) The y coordinate can be derived by substituting in the projected plane.

Additionally, the processor 140 may derive the z coordinate based on the first distance value of the first anchor set and the second distance value of the second anchor set, and finally derive the coordinates of the space where the tag is located. .

At this time, in one embodiment, the distance between anchors in the anchor set can be adjusted according to the size of the space to be projected (to be localized) or the positioning accuracy, and the resolution of the layer to be projected can be improved by adjusting the distance between anchors. .

Meanwhile, the signal emitted from the tag can be divided into LOS (line-of-sight), which is received directly, and NLOS (non-line-of-sight), which is received through reflection, transmission, and refraction.

These LOS/NLOS signals are slower than the typical speed of propagation through the air, which may cause the predicted distance to be longer than the actual distance. In other words, signals composed of LOS/NLOS are the main cause of errors in location prediction depending on the survey method.

Because of any obstacle or material that changes the refraction of the signal, it can be difficult to calculate the correct distance or arrival speed for the space you want to measure. In other words, location measurement may be difficult using algorithms such as triangulation/trilateration due to various environments.

Accordingly, the processor 140 can determine the state of the signal and derive the position in the projected space based on a deep neural network.

Due to the projection space and obstacles (cement, glass, wood, etc.) depending on the space in which you want to use the anchor set to determine the location of the tag, the signal the anchor receives may contain noise or errors in LOS/NLOS and RSSI. .

To process this, algorithms such as signal-to-noise ratio, received signal strength, and delay processing due to obstacles can be used, but these algorithms are difficult to respond to various environments, and the parameters of some algorithms are manually defined by humans.

Therefore, the processor 140 collects learning data about the distance of the received signal, RSSI, and the environment of the anchor set location according to the obstacle material through experiment and learning, and determines the position of the deep neural network based on correction according to the obstacle material. You can train a model.

That is, the processor 140 can calculate the location of the tag based on the relative relationship of the received signal and the location of the anchor through the location determination model.

This location determination model is: {Structural location of the anchor set}, {Received signal from the tag, expected distance from the tag according to the speed of propagation in the air}, {RSSI from the tag}, {Signal components between anchors in the anchor set : Propagation speed} as input data, and may be a learning model trained to output {position of tag: x, y, z}, {position reliability, quality of propagation component}. Here, regarding the structural position of the anchor set among the input data, the position of each anchor can be automatically calculated according to the structure of the preset anchor set. The structure of a preset anchor set may mean a coordinate system based on the anchor set.

That is, the processor 140 uses at least one of the structural position of the anchor set, the received signal from the tag, the expected distance from the tag according to the speed of propagation in the air, RSSI, and signal components between anchors in the anchor set as input data. , the positioning of the tag can be performed using a deep neural network-based positioning model that is pre-trained to output the tag's location, location reliability, and radio wave component quality.

At this time, the positioning model may be trained through training data labeling at least one of the distance of the received signal, RSSI, and learning data about the environment of the anchor set location as an obstacle material.

Meanwhile, in one embodiment, for example, in the test of the positioning model, the general 6 Full Connected Layers and 2 Dropouts may be applied, and the first anchor set (A, B) and the second anchor set (C, D) ) MSE Loss, A, B, C, D integrated MSE Loss can be applied. Additionally, in one embodiment, the neural network can be changed and applied according to more environmental factors (e.g., weather effects, seasonal effects, etc.).

In addition, according to the embodiment, the previously learned deep neural network-based positioning model may include the structural position of the movable anchor set including the first anchor set and the second anchor set, and the first and second anchors of the movable anchor set. When the received signal from the tag for each set is input, the tag position in the projection plane derived based on the structural position of the anchor set and the received signal from the tag is queried as input, and the tag position in the projection plane is It may be a learning model trained to output a tag location positioning result in a 3D space based on an anchor set for the tag location.

Here, deep neural network learning (deep learning) technology can learn down to a deep level in multiple stages based on data. Deep learning can represent a set of machine learning algorithms that extract key data from multiple pieces of data at higher levels.

The deep learning structure may include an artificial neural network (ANN). For example, the deep learning structure consists of deep neural networks (DNN) such as convolutional neural network (CNN), recurrent neural network (RNN), and deep belief network (DBN). It can be. The deep learning structure according to one embodiment may use various known structures. That is, the positioning system 1 may be equipped with an artificial neural network, that is, the processor 140 of the present embodiment is an artificial neural network, for example, a deep neural network such as CNN, RNN, DBN, etc. DNN) may be included. Both unsupervised learning and supervised learning can be used as machine learning methods for these artificial neural networks. In this embodiment, the artificial neural network structure can be controlled to be updated after learning according to the settings.

Figure 7 is a flowchart for explaining a location determination method according to an embodiment.

Referring to FIG. 7, in step S100, the processor 140 receives a signal from a tag in a movable anchor set that can move within a set range in three-dimensional space.

In one embodiment, positioning is performed through a set of mobile anchors that do not require prior installation, and spatial analysis using the Projection method and Homography, a camera/computer vision algorithm applied for positioning (( Positioning can be performed through (decomposition into (x, y, depth) rather than x, y, z) and multi-projective layer.

That is, the movable anchor set of one embodiment includes at least four anchors and may be composed of a first anchor set for plane positioning and a second anchor set for plane correction and space configuration.

In step S200, the processor 140 converts the tag signal information in the 3D space into a 3D space based on the mobile anchor set based on a homography algorithm, and derives the coordinates of the tag in the 3D space based on the mobile anchor set.

At this time, the processor 140 projects the tag signal information in the 3D space onto the movable anchor set reference plane using a projection matrix, and uses a homography matrix to project the 3D space based on the movable anchor set reference plane. Tag signal information can be reconstructed.

Additionally, the processor 140 may perform positioning on a plane using a first anchor set and height positioning on a plane measured using a second anchor set located behind the first anchor set based on the tag direction. there is.

More specifically, the processor 140 may measure a first distance value, which is the horizontal plane distance, using the first anchor set, and measure a second distance value, which is the vertical plane distance, using the second anchor set. .

And processor 140 derives the , and the z-coordinate of the tag can be derived based on the first distance value and the second distance value.

In step S300, the processor 140 based on the derived coordinates of the tag. Positioning is performed by correcting losses due to obstacles.

For example, in one embodiment, processing a signal received at two sets of anchors, processing a signal to measure a two-dimensional position at each set of anchors, processing a signal integrating the two sets of anchors, and obtaining three-dimensional coordinates. A neural network can be applied for this.

The processor 140 may predict the state of a signal received from a tag in the second anchor set based on the line-of-sight/non-line-of-sight (LOS/NLOS) ratio of the signal received from the tag in the second anchor set. Additionally, the processor 140 may correct loss caused by obstacles based on the RSSI value in the second anchor set and the signal state between anchors.

At this time, the processor 140 may perform positioning of the tag by reflecting loss due to obstacles based on a previously learned deep neural network-based positioning model.

The processor 140 uses as input data at least one of the structural position of the mobile anchor set, the received signal from the tag, the expected distance from the tag according to the speed of propagation in the air, RSSI, and signal components between anchors in the mobile anchor set. , the location of the tag can be performed based on a deep neural network-based location location model that is pre-trained to output the location, location reliability, and radio wave component quality of the tag.

At this time, the deep neural network-based positioning model may be trained using training data that labels at least one of the distance of the received signal, RSSI, and learning data about the environment of the mobile anchor set location as an obstacle material.

Meanwhile, in one embodiment, the previously learned deep neural network-based positioning model includes the structural location of the movable anchor set including the first anchor set and the second anchor set, and the first and second anchor sets of the movable anchor set. When the received signal from each tag is input, the tag position in the projection plane derived based on the structural position of the mobile anchor set and the received signal from the tag is queried as input, and the tag position in the projection plane is determined. It may be a learning model learned to output tag positioning results in a three-dimensional space based on a set of mobile anchors.

In other words, the location determination technology in one embodiment can immediately determine the location of a worker when a collapse accident occurs at an industrial site based on the tag. In addition, in order to find a person in distress on a mountain, the anchor set can be used to rotate or move about the space to be projected to find the location of the person in distress, or conversely, it can guide a hiker who is lost in the mountain to the correct location. Above all, when a fire breaks out, it is possible to direct the safety of firefighters and firefighting activities in real time by placing them at the fire scene and projecting the space to determine the real-time location of firefighters deployed within the building.

As described above, the location determination device 100 of one embodiment may be able to expand its scope of use through a UWB-based location determination method, ideas, and hardware production method.

In particular, it will be possible to resolve the inconvenience of installing a UWB anchor in indoor positioning.

The embodiments according to the present disclosure described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. At this time, the media includes magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and ROM. , RAM, flash memory, etc., may include hardware devices specifically configured to store and execute program instructions.

Meanwhile, the computer program may be specially designed and configured for the present disclosure, or may be known and usable by those skilled in the art of computer software. Examples of computer programs may include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

In the specification (particularly in the claims) of the present disclosure, the use of the term “above” and similar referential terms may refer to both the singular and the plural. In addition, when a range is described in the present disclosure, the invention includes the application of individual values within the range (unless there is a statement to the contrary), and each individual value constituting the range is described in the detailed description of the invention. It's the same.

Unless there is an explicit order or description to the contrary regarding the steps constituting the method according to the present disclosure, the steps may be performed in any suitable order. The present disclosure is not necessarily limited by the order of description of the steps above. The use of any examples or illustrative terms (e.g., etc.) in the present disclosure is merely to describe the present disclosure in detail, and unless limited by the claims, the scope of the present disclosure is limited by the examples or illustrative terms. It doesn't work. Additionally, those skilled in the art will appreciate that various modifications, combinations and changes may be made according to design conditions and factors within the scope of the appended claims or their equivalents.

Therefore, the spirit of the present disclosure should not be limited to the above-described embodiments, and the scope of the patent claims described below as well as all scopes equivalent to or equivalently changed from the claims are within the scope of the spirit of the present disclosure. It will be said to belong to

1: Location determination system
100: location determination device
110: communication interface
120: user interface
130: memory
140: processor
200: user terminal
300: Server
400: Network

Claims (19)

A positioning method that performs positioning of a tag in an arbitrary three-dimensional space based on ultra-wide band (UWB) wireless technology, in which at least part of each step is performed by a processor, comprising:
Receiving a signal from the tag in a movable anchor set capable of moving within a set range in the three-dimensional space; and
Based on a homography algorithm, converting the tag signal information in the three-dimensional space into a three-dimensional space based on the mobile anchor set, and deriving the coordinates of the tag in the three-dimensional space based on the mobile anchor set,
Location determination method. According to claim 1,
The movable anchor set includes at least four anchors and consists of a first anchor set for plane positioning and a second anchor set for plane correction and space construction,
Location determination method. According to claim 2,
The step of deriving the coordinates of the tag in a three-dimensional space based on the mobile anchor set,
Projecting the tag signal information in the three-dimensional space onto the mobile anchor set reference plane using a projection matrix; and
Comprising the step of reconstructing the tag signal information in a three-dimensional space based on the mobile anchor set reference plane based on the mobile anchor set reference plane using a homography matrix,
Location determination method. According to claim 2,
The step of deriving the coordinates of the tag in a three-dimensional space based on the mobile anchor set,
performing positioning with respect to a plane with the first anchor set; and
Comprising the step of performing height positioning on a plane measured with the second anchor set located behind the first anchor set based on the tag direction,
Location determination method. According to claim 4,
The step of deriving the coordinates of the tag in a three-dimensional space based on the mobile anchor set,
measuring a first distance value, which is a plane distance with respect to the horizontal, using the first anchor set;
measuring a second distance value, which is a plane distance with respect to the vertical, using the second anchor set;
deriving an x-coordinate of the tag in a projected plane by signals received between anchors of the first anchor set;
deriving a y coordinate of the tag in a projected plane by signals received between anchors of the second anchor set; and
Comprising the step of deriving the z coordinate of the tag based on the first distance value and the second distance value,
Location determination method. According to claim 5,
Based on the coordinates of the tag derived above. It further includes the step of performing location determination by correcting loss due to obstacles,
The step of performing location determination by correcting the loss due to the obstacle is,
predicting a state of a signal received from the tag in the second anchor set based on a line-of-sight/non-line-of-sight (LOS/NLOS) ratio of the signal received from the tag in the second anchor set; and
Comprising the step of correcting loss due to obstacles based on the RSSI (received signal strength) value in the second anchor set and the signal state between anchors,
Location determination method. According to claim 6,
The step of performing location determination by correcting the loss due to the obstacle is,
Based on a previously learned deep neural network-based positioning model, comprising performing positioning of the tag by reflecting loss due to the obstacle,
Location determination method. According to claim 7,
The step of performing location determination by correcting the loss due to the obstacle is,
Position of the tag using at least one of the following as input data: structural position of the mobile anchor set, received signal from the tag, expected distance from the tag according to the speed of propagation in the air, RSSI, and signal components between anchors in the mobile anchor set. , performing location determination of the tag based on a deep neural network-based location determination model that is pre-trained to output location reliability and radio wave component quality,
The deep neural network-based positioning model is trained through training data labeling at least one of the distance of the received signal, RSSI, and learning data about the environment of the mobile anchor set location as an obstacle material,
Location determination method. According to claim 7,
The pre-learned deep neural network-based positioning model is based on the structural position of the mobile anchor set including the first anchor set and the second anchor set and the tags for each of the first and second anchor sets of the mobile anchor set. When the received signal is input, the tag position in the projection plane derived based on the structural position of the mobile anchor set and the received signal from the tag is queried as input, and the tag position in the projection plane is queried as input. A learning model trained to output tag positioning results in three-dimensional space based on a set of mobile anchors,
Location determination method. A computer-readable recording medium having recorded thereon a program that, when executed by at least one processor, causes the at least one processor to perform the method of any one of claims 1 to 9. A positioning device that performs positioning of a tag in an arbitrary three-dimensional space based on ultra-wide band (UWB) wireless technology,
Memory; and
A processor connected to the memory and configured to execute computer-readable instructions contained in the memory,
The at least one processor,
An operation of receiving a signal from the tag in a movable anchor set capable of moving within a set range in the three-dimensional space, and
Based on a homography algorithm, the tag signal information in the three-dimensional space is converted into a three-dimensional space based on the mobile anchor set, and the operation of deriving the coordinates of the tag in the three-dimensional space based on the mobile anchor set is set to be performed. ,
Location determination device. According to claim 11,
The movable anchor set includes at least four anchors and consists of a first anchor set for plane positioning and a second anchor set for plane correction and space construction,
Location determination device. According to claim 12,
The operation of deriving the coordinates of the tag in a three-dimensional space based on the mobile anchor set,
Projecting the tag signal information in the three-dimensional space onto the mobile anchor set reference plane using a projection matrix, and
Comprising the operation of reconstructing the tag signal information in a three-dimensional space based on the mobile anchor set reference plane using a homography matrix,
Location determination device. According to claim 12,
The operation of deriving the coordinates of the tag in a three-dimensional space based on the mobile anchor set,
An operation of performing positioning with respect to a plane with the first anchor set, and
Comprising an operation of performing height positioning on a plane measured by the second anchor set located behind the first anchor set based on the tag direction,
Location determination device. According to claim 14,
The operation of deriving the coordinates of the tag in a three-dimensional space based on the mobile anchor set,
An operation of measuring a first distance value, which is a plane distance with respect to the horizontal, using the first anchor set,
An operation of measuring a second distance value, which is a plane distance with respect to the vertical, using the second anchor set,
deriving an x-coordinate of the tag in a plane projected by signals received between anchors of the first anchor set;
deriving a y coordinate of the tag in a plane projected by signals received between anchors of the second anchor set, and
Including the operation of deriving the z coordinate of the tag based on the first distance value and the second distance value,
Location determination device. According to claim 15,
The at least one processor,
Based on the coordinates of the tag derived above. It is set to further perform an operation to perform location determination by compensating for loss due to obstacles,
The operation of performing location determination by correcting the loss due to the obstacle is,
Predicting the state of a signal received from the tag in the second anchor set based on the line-of-sight/non-line-of-sight (LOS/NLOS) ratio of the signal received from the tag in the second anchor set, and
Comprising an operation of correcting loss due to obstacles based on the RSSI (received signal strength) value in the second anchor set and the signal state between anchors,
Location determination device. According to claim 16,
The operation of performing location determination by correcting the loss due to the obstacle is,
Based on a previously learned deep neural network-based positioning model, including the operation of performing positioning of the tag by reflecting loss due to the obstacle,
Location determination device. According to claim 17,
The operation of performing location determination by correcting the loss due to the obstacle is,
Position of the tag using at least one of the following as input data: structural position of the mobile anchor set, received signal from the tag, expected distance from the tag according to the speed of propagation in the air, RSSI, and signal components between anchors in the mobile anchor set. , an operation of performing location determination of the tag based on a deep neural network-based location location model trained in advance to output location reliability and radio wave component quality,
The deep neural network-based positioning model is trained through training data labeling at least one of the distance of the received signal, RSSI, and learning data about the environment of the mobile anchor set location as an obstacle material,
Location determination device. According to claim 17,
The pre-learned deep neural network-based positioning model is based on the structural position of the mobile anchor set including the first anchor set and the second anchor set and the tags for each of the first and second anchor sets of the mobile anchor set. When the received signal is input, the tag position in the projection plane derived based on the structural position of the mobile anchor set and the received signal from the tag is queried as input, and the tag position in the projection plane is queried as input. A learning model trained to output tag positioning results in three-dimensional space based on a set of mobile anchors,
Location determination device.

Images